Learning dislocation dynamics mobility laws from large-scale MD simulations

By dispensing with all the atoms and only focusing on dislocation lines, the computational method of Discrete Dislocation Dynamics (DDD) gains greatly over Molecular Dynamics (MD) in simulation efficiency of metal plasticity. But whereas in MD dislocations follow natural dynamics of atomic motion, DDD must rely on a dislocation mobility function to prescribe how a dislocation line should respond to the driving force exerted on it. However, reflecting our still incomplete understanding of ways in which dislocations move, mobility functions presently employed in DDD simulations entail simplifications and approximations of limited or, worse still, unknown accuracy and applicability. Here we introduce a data-driven approach in which the dislocation mobility function is modeled as a graph neural network (GNN) trained on large-scale MD simulations of crystal plasticity. We apply our proposed approach to predicting plastic strength of body-centered-cubic (BCC) metal tungsten and show that, once implemented in a DDD model, our GNN dislocation mobility function accurately reproduces the challenging tension/compression asymmetry of plastic flow observed both in ground-truth MD simulations and in experiment. Furthermore, subsequently validated by MD simulations, the same function accurately predicts plastic response of tungsten under conditions not previously seen in training. By demonstrating its ability to learn relevant physics of dislocation motion, our DDD+ML approach opens a promising avenue to bringing fidelity of DDD models closer in line with direct MD simulations at a much reduced computational cost.